WO2018221066A1 - 調剤監査支援装置及び調剤監査支援方法 - Google Patents

調剤監査支援装置及び調剤監査支援方法 Download PDF

Info

Publication number
WO2018221066A1
WO2018221066A1 PCT/JP2018/016282 JP2018016282W WO2018221066A1 WO 2018221066 A1 WO2018221066 A1 WO 2018221066A1 JP 2018016282 W JP2018016282 W JP 2018016282W WO 2018221066 A1 WO2018221066 A1 WO 2018221066A1
Authority
WO
WIPO (PCT)
Prior art keywords
region
interest
medicine
template
image
Prior art date
Application number
PCT/JP2018/016282
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
一央 岩見
Original Assignee
富士フイルム株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 富士フイルム株式会社 filed Critical 富士フイルム株式会社
Priority to JP2019522022A priority Critical patent/JP6757851B2/ja
Priority to EP18809549.1A priority patent/EP3633609A1/en
Priority to CN201880029204.4A priority patent/CN110603567B/zh
Publication of WO2018221066A1 publication Critical patent/WO2018221066A1/ja
Priority to US16/662,233 priority patent/US11594322B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61J—CONTAINERS SPECIALLY ADAPTED FOR MEDICAL OR PHARMACEUTICAL PURPOSES; DEVICES OR METHODS SPECIALLY ADAPTED FOR BRINGING PHARMACEUTICAL PRODUCTS INTO PARTICULAR PHYSICAL OR ADMINISTERING FORMS; DEVICES FOR ADMINISTERING FOOD OR MEDICINES ORALLY; BABY COMFORTERS; DEVICES FOR RECEIVING SPITTLE
    • A61J3/00—Devices or methods specially adapted for bringing pharmaceutical products into particular physical or administering forms
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/85—Investigating moving fluids or granular solids
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G16H20/13—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered from dispensers
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination

Definitions

  • the present invention relates to a dispensing audit support device and a dispensing audit support method, and in particular, a dispensing that supports an audit of whether or not a photographed medicine is a medicine as prescribed by comparing a photographed image with a master image.
  • the present invention relates to an audit support apparatus and a dispensing audit support method.
  • Patent Document 1 describes an apparatus for selecting a test object by converting the orthogonal coordinates to cylindrical coordinates and extracting the outline to reduce the influence of the rotation component and perform the selection with high accuracy.
  • the collation between the captured image and the master image can be performed by, for example, setting a region of interest for the captured image, setting a template for the master image, and collating the region of interest with the template.
  • a collation since the distortion of the drug shape, blur, reflection of the edge, etc. occur depending on the collation conditions such as the position of the collation target drug in the image, in order to perform collation with high accuracy, It is necessary to set an appropriate region of interest and template according to the matching conditions.
  • Patent Document 1 described above the medicine master image and the captured image are collated, but setting the region of interest and the template according to the collation conditions is not considered.
  • Patent Document 2 what is to be checked in the dispensing inspection of a medicine (tablet) is not a contour but a stamped portion. Even if the stamped portion is converted into a cylindrical coordinate system, the stamp changes depending on the positional relationship with the light source. Therefore, the collation accuracy is not improved. As described above, in the conventional technique, the collation accuracy greatly depends on the collation conditions, and the robustness of the collation accuracy is low.
  • the present invention has been made in view of such circumstances, and an object thereof is to provide a dispensing audit support device and a dispensing audit support method with high robustness of collation accuracy.
  • the dispensing inspection support apparatus includes a master image storage unit that stores a master image indicating a medicine, and imaging that captures the audited medicine and acquires a captured image.
  • a region of interest, a region of a region of interest for setting a region of interest in the image of the agent to be audited, and detecting the position, shape, and size of the region of interest A region-of-interest setting unit that is set based on the position of the medicine, and a template generation unit that reads a master image indicating the medicine described in the prescription from the master image storage unit and generates a template based on the read master image.
  • the template generation unit that sets the position, shape, and size of the template corresponding to the set region of interest is compared with the template and the region of interest to supervise Comprising a matching unit that is a drug indicated subject agents and master image and outputs the information indicating whether or not the same, the.
  • the position, the shape, and the size of the region of interest are set according to the position of the inspection target medicine (check target medicine) in the captured image, and the position of the master image corresponding to the set region of interest. Since the shape and size are set, it is possible to avoid or reduce drug shape distortion, blur, and edge reflection due to the position of the audited drug. Therefore, the influence on the collation accuracy by the collation conditions is small, and the robustness of the collation accuracy can be increased.
  • the dispensing inspection support apparatus is the first aspect, in which the region-of-interest setting unit sets the region of interest as the distance between the detected position of the medicine to be audited and the center of the captured image increases, and generates a template.
  • the part generates a smaller template as the set region of interest is smaller. If the distance between the audited drug and the center of the captured image is too long, the audited drug may appear to be distorted, blurred, or the side of the drug may be reflected. If the region of interest and the template are set in the same size as the case, the region of interest and the template include a region where such a problem occurs, and the matching cannot be performed with high accuracy.
  • the second aspect by setting a region of interest small and further setting a template corresponding to such a region of interest, it is possible to avoid a region where the above-described problem occurs and The collation can be performed with high accuracy even when the medicine is far from the center of the captured image.
  • the region-of-interest setting unit increases the distance between the detected position of the auditable drug and the center of the photographed image, and the image of the auditable drug
  • the region of interest is set by moving the region of interest in the direction of the center of the captured image, and the template generation unit generates a template that is largely moved with respect to the master image as the amount of movement of the region of interest increases. If the distance between the audited drug and the center of the captured image is long, the image of the auditable drug may be greatly blurred from the side far from the center, as in the case where the distance is short in this situation If a region of interest and a template are set, collation cannot be performed with high accuracy.
  • the dispensing inspection support apparatus is any one of the first to third aspects, wherein the region-of-interest setting unit moves the position of the region of interest in the photographed image based on the direction of illumination with respect to the audited drug.
  • the template generation unit moves the position of the template with respect to the master image in correspondence with the movement of the region of interest. Even if it is difficult to grasp the characteristics of the drug due to the relationship with the illumination at the time of collation and the collation accuracy is lowered, the position of the region of interest is moved as in the fourth aspect to correspond to the movement of the region of interest. Therefore, it is possible to avoid such a problem by moving the position of the template, and collation can be performed with high accuracy.
  • the dispensing inspection support apparatus is any one of the first to fourth aspects, wherein the region-of-interest setting unit and the template generation unit determine the distance between the position of the medicine to be audited and the center of the captured image. If the threshold is less than the threshold, set the region of interest and template to be similar to the audited drug, and if the distance between the position of the audited drug and the center of the captured image exceeds the threshold, set the region of interest and template respectively. Set to rectangle.
  • the region of interest and the template may be similar to the auditable drug because the shape of the drug in the captured image is close to the true shape of the drug
  • the medicine to be inspected is far from the center of the photographed image (when the distance exceeds the threshold)
  • there may be a problem that the shape of the medicine is distorted in the photographed image or the end (side surface) is reflected.
  • such a problem can be avoided by setting a region of interest as in the fifth aspect and setting a template corresponding to the region of interest, and collation can be performed with high accuracy. it can.
  • the dispensing inspection support apparatus is the orientation of the region of interest and the template by rotating at least one of the region of interest and the template. Are matched. According to the sixth aspect, accurate matching can be performed by matching the direction of the region of interest and the template.
  • the dispensing audit support apparatus is configured such that the collating unit expands or contracts at least one of the region of interest and the template to reduce the region of interest and the template. Match by matching the size of. According to the seventh aspect, accurate matching can be performed by matching the size of the region of interest and the template.
  • the template and the region of interest include a marking area indicating a marking applied to the medicine.
  • the inscription applied to the medicine is effective as a key for collation
  • the region of interest and the template include the inscription region as in the eighth aspect, so that accurate collation can be performed.
  • the dispensing audit support apparatus is based on an image photographed under illumination used when collating the medicine to be audited by the photographing unit. It is an image.
  • the illumination during the master image photographing and the illumination during the collation are performed. It is possible to match, and an appropriate master image can be acquired to improve collation accuracy.
  • a dispensing inspection support method includes a master image storage unit that stores a master image indicating a medicine, and a photographing that photographs the audited medicine and obtains a photographed image.
  • a dispensing audit support method using a dispensing audit support device wherein the dispensing audit support device detects a position of a drug to be audited in a captured image, and the dispensing audit support device displays an image of the audited drug.
  • a region-of-interest setting step for setting a region of interest for setting the position, shape, and size of the region of interest based on the position of the detected drug, and a dispensing inspection support device described in the prescription
  • Agent audit support apparatus by matching the template region of interest, having a matching step of the drug indicating drug and the master image represented by the captured image to output the information indicating whether it is the same.
  • the influence on the collation accuracy due to the position of the collation target medicine is small, and the robustness of the collation accuracy can be increased.
  • a program for causing a dispensing audit support apparatus (computer) to execute the dispensing audit support method according to the tenth aspect and a non-temporary recording medium on which a computer-readable code of the program is recorded are also cited as aspects of the present invention. be able to.
  • the robustness of the collation accuracy can be increased.
  • FIG. 1 is a block diagram showing the configuration of a dispensing inspection support apparatus according to an embodiment of the present invention.
  • FIG. 2 is a diagram illustrating a state in which an image of a sachet is acquired under illumination.
  • FIG. 3 is another diagram illustrating a state in which an image of a packaging bag is acquired under illumination.
  • FIG. 4 is a diagram illustrating a functional configuration of the processing unit.
  • FIG. 5 is a diagram illustrating information stored in the storage unit.
  • FIG. 6 is a flowchart showing processing of the dispensing audit support method.
  • FIG. 7 is a diagram showing a medicine master image and attribute information.
  • FIG. 8 is a flowchart showing a region of interest and template setting process.
  • FIG. 1 is a block diagram showing the configuration of a dispensing inspection support apparatus according to an embodiment of the present invention.
  • FIG. 2 is a diagram illustrating a state in which an image of a sachet is acquired under illumination.
  • FIG. 3 is
  • FIG. 10A is a diagram illustrating setting of a region of interest according to the position of a medicine.
  • FIG. 10B is a diagram illustrating setting of a region of interest according to the position of a medicine.
  • FIG. 11A is another diagram illustrating setting of a region of interest according to the position of a medicine.
  • FIG. 11B is another diagram showing the setting of the region of interest according to the position of the medicine.
  • FIG. 12A is still another diagram showing the setting of the region of interest according to the position of the medicine.
  • FIG. 12B is still another diagram showing the setting of the region of interest according to the position of the medicine.
  • FIG. 13 is a diagram illustrating a display example of the matching result.
  • FIG. 1 is a diagram showing a configuration of a dispensing audit support device 1 (dispensing audit support device) according to an embodiment of the present invention.
  • the dispensing inspection support apparatus 1 includes a processing unit 10 (imaging unit, drug detection unit, region of interest setting unit, template generation unit, collation unit), storage unit 20 (master image storage unit), display unit 30, and operation unit 40.
  • the processing unit 10 is connected to the illumination unit 12, the camera 15A (imaging unit), the camera 15B (imaging unit), and the prescription reader 16.
  • the camera 15A and the camera 15B are constituted by digital cameras. As shown in FIG. 2, the camera 15A is arranged on the upper side (+ Z side in FIG. 2) of the medicine bandage PB in which the sachets TP (medicine bags) are continuously formed, and the lower side (FIG. 2). The camera 15B is disposed on the ⁇ Z side) and photographs the medicine packaged in the packaging bag TP from above and below (a plurality of different directions).
  • the packaging bag TP (medicine bandage PB) is conveyed by the conveyance mechanism 50 in the + X direction in FIG. 2 (the X axis is an axis along the longitudinal direction of the medicinal bandage PB).
  • the light source 13 illuminates the packaging bag TP from four directions ( ⁇ X direction and ⁇ Y direction).
  • the prescription reader 16 reads prescription information. For example, by OCR (Optical Character Recognition), information such as a patient name, a prescribed medicine and its quantity is read from a prescription written on paper. When a barcode or the like indicating information related to the prescribed medicine is recorded in the prescription, information such as the prescribed medicine and its quantity may be read from the barcode. Alternatively, the user may read the prescription and input prescription information using an input device such as a keyboard of the operation unit 40.
  • OCR Optical Character Recognition
  • FIG. 4 is a diagram illustrating a functional configuration of the processing unit 10.
  • the processing unit 10 includes a prescription information input unit 10A, an imaging unit 10B (imaging unit), a drug detection unit 10C (drug detection unit), a region of interest setting unit 10D (region of interest setting unit), and a template generation unit 10E ( A template generation unit), a collation unit 10F (collation unit), a display control unit 10G, and a communication unit 10H.
  • EEPROM Electrically Erasable and Programmable Read Only Memory
  • CPU Central Processing Unit
  • ROM Read Only Memory: non-temporary recording medium
  • RAM Random Access Memory
  • the prescription information input unit 10A controls the prescription reader 16 to input information (for example, patient name, drug identification information and quantity, usage, etc.) described in the prescription.
  • the photographing unit 10B controls the camera 15A and the camera 15B to photograph the medicine to be audited packaged in the packaging bag TP, and obtains a photographed image.
  • the drug detection unit 10C detects the position of the audit target drug in the captured image acquired by the imaging unit 10B. The orientation may be detected in addition to the position of the medicine to be audited.
  • the region-of-interest setting unit 10D sets the position, shape, and size of the region of interest with respect to the image of the audited drug based on the position detected by the drug detection unit 10C.
  • the template generation unit 10E reads a master image indicating the medicine described in the prescription, and generates a template based on the read master image.
  • the collation unit 10F collates the template with the region of interest, and outputs information indicating whether or not the medicine to be audited and the medicine indicated by the master image are the same.
  • the display control unit 10G performs display control such as a collation result.
  • the communication unit 10H communicates with a server, a database, and the like (not shown) via a network, and acquires information such as a medicine master image and attribute information. Detailed processing of the dispensing audit support method by these functions will be described later.
  • the functions of the processing unit 10 described above can be realized by using various processors.
  • the various processors include, for example, a CPU (Central Processing Unit) that is a general-purpose processor that executes various types of functions by executing software (programs).
  • the various processors described above also include a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacturing, such as an FPGA (Field Programmable Gate Array).
  • PLD programmable logic device
  • FPGA Field Programmable Gate Array
  • the above-mentioned various processors include dedicated electric circuits, which are processors having a circuit configuration designed exclusively for executing specific processing such as ASIC (Application Specific Specific Integrated Circuit).
  • each unit may be realized by a single processor, or may be realized by combining a plurality of processors.
  • a plurality of functions may be realized by one processor.
  • a processor As an example of configuring a plurality of functions by one processor, first, as represented by a computer such as a client and a server, one processor is configured by a combination of one or more CPUs and software. Is realized as a plurality of functions.
  • SoC system-on-chip
  • the function of each unit is configured using one or more of the various processors described above as a hardware structure.
  • a computer-readable code of a program for causing the dispensing audit support apparatus (computer) to execute the dispensing audit support method according to the present invention is a non-illustrated ROM (Read Only Memory) or the like. It is recorded on a temporary recording medium.
  • the storage unit 20 includes a non-temporary recording medium such as a CD (Compact Disk), a DVD (Digital Versatile Disk), a hard disk (Hard Disk), and various semiconductor memories and a control unit thereof. Store it in association.
  • the prescription information 20A is information read through the prescription reader 16, and includes, for example, the patient name, drug identification information and quantity, usage, and the like.
  • the master image 20B is a medicine master image or a processed master image obtained by performing image processing on the master image. Examples of the attribute information 20C include, but are not limited to, the drug type, shape, size, color, and stamp of the drug.
  • the medicine image 20D is a captured image and / or an image of an inspection target medicine extracted from the captured image.
  • the collation result 20E is information indicating the collation result created by the processing unit 10.
  • the storage unit 20 may store information on a region of interest and / or a template. During processing by the processing unit 10, these images and information are read and written between the processing unit 10 and the storage unit 20.
  • the display unit 30 includes a monitor 32, and can display prescription information read via the prescription reader 16, images of packaged medicines, information and images stored in the storage unit 20, verification results, and the like.
  • the operation unit 40 includes a pointing device such as a mouse and an input device such as a keyboard. The user can operate an image, a button, and the like displayed on the monitor 32 with the operation unit 40.
  • FIG. 6 is a flowchart showing the processing of the dispensing audit support method.
  • step S100 prescription information is input by the prescription reader 16 and the processing unit 10 (prescription information input unit 10A).
  • the prescription information 20 ⁇ / b> A already stored in the storage unit 20 may be read.
  • the photographing unit 10B controls the cameras 15A and 15B to photograph the medicine packaged in the packaging bag TP of the medicine bandage PB from a plurality of directions (up and down directions) and acquire images.
  • step S120 based on the prescription information read in step S100, a master image of the medicine described in the prescription is acquired.
  • the master image to be acquired may be the master image 20B stored in the storage unit 20, or may be an image acquired from an external drug database or the like via the processing unit 10 (communication unit 10H).
  • the image acquired as the master image is an image (taken based on an image obtained by photographing the medicine to be inspected under the light source 13 (light source of illumination used for collation) by the cameras 15A and 15B and the processing unit 10 (imaging unit 10B).
  • an image based on an image taken in the vicinity of the center of the field of view of the cameras 15A and 15B is preferably used as the master image.
  • FIG. 7 is an example of a master image, and includes a plurality of images (master images iM1, iM2) acquired by photographing the medicine T1 from different directions (up and down directions of the medicine).
  • the master image iM1 is an image about the front surface of the medicine T1
  • the master image iM2 is an image about the back surface of the medicine.
  • attribute information (attribute information 20C: see FIG. 5) indicating the attribute of the medicine T1 is associated with the master images iM1 and iM2, and the processing unit 10 (display control unit 10G)
  • the master image and the attribute information are displayed on the monitor 32 in accordance with the user's operation via.
  • the processing unit 10 extracts a drug region of each drug from the captured image, performs image processing such as enlargement or reduction, brightness adjustment, and the like as necessary to acquire images of individual drugs.
  • Step S130 drug detection step. If the image of each medicine is acquired, processing part 10 (medicine detection part 10C) will detect the position of the medicine for inspection in a photography picture (Step S140: medicine detection process). In step S140, for example, the edge of the medicine is detected and its center is obtained, and the position of the obtained center can be detected as the position of the medicine to be audited.
  • step S150 region of interest setting step, template setting step.
  • step S151 the processing unit 10 (region of interest setting unit 10D) calculates the distance between the drug and the center of the captured image based on the position of the drug detected in step S150, and the calculated distance is equal to or less than the threshold value. Whether or not (step S152). If the determination is affirmed (YES in step S152), the processing unit 10 (region-of-interest setting unit 10D) sets the region of interest to be similar to the auditable drug (step S153: region-of-interest setting step). Further, the processing unit 10 (template generation unit 10E) sets the template for the master image to be similar to the audit target drug in correspondence with the shape of the region of interest (step S154: template generation step).
  • Similar shape to drug to be audited means, for example, if the drug is circular, the region of interest (or template) has a different size, and if the drug is oval, the region of interest (or template) also has a different size. It means that there is.
  • step S152 determines whether the processing unit 10 (region of interest setting unit 10D) is negative (when the calculated distance exceeds the threshold value).
  • step S155 region of interest setting step.
  • a template for the master image is set to a rectangle corresponding to the rectangular region of interest (step S156: template generation step).
  • the processing unit 10 determines the position of the region of interest as the center of the captured image as the distance between the drug and the center of the captured image increases. And the region of interest is set smaller (step S157: region of interest setting step).
  • the size of the region of interest can be, for example, r ⁇ sin ⁇ , 0.5 ⁇ r ⁇ sin ⁇ , etc., where r is the radius of the drug and ⁇ is the angle between the drug and the imaging optical axis PA. .
  • the processing unit 10 (template generation unit 10E) generates a template having a position, size, and shape corresponding to the position, size, and shape of the region of interest (step S158: template generation step).
  • steps S151 to S158 will be further described. If the medicine T1 has a three-dimensional structure (having a thickness and a curved surface) as shown in the sectional view of FIG. 9, the medicine T1 is located far from the center of the field of view (imaging optical axis PA) (FIG. 9). Then, in the ⁇ X direction), the influence of the light L from the light source in the ⁇ X direction of the light source 13 (see FIG. 3) becomes strong. Considering the light L, in FIG. 9, the light L is obliquely incident on the marks F2 and F3, so that a shadow is formed.
  • the position of the region of interest based on the position of the drug,
  • the size and shape are set, and the position, size and shape of the template are set corresponding to the region of interest.
  • a setting example of a region of interest and a template will be specifically described.
  • FIG. 10A and 10B are diagrams illustrating an example of setting a region of interest based on the position of a medicine.
  • FIG. 10A shows the interest when the medicine T1 is present at the center, the middle, and the end of the photographed image iT1 (capturing bag TP photographed from the + Z direction) (respectively denoted by T1A, T1B, and T1C).
  • T1A, T1B, and T1C An example of setting the area is shown.
  • the processing unit 10 sets the region of interest RA to a circle that is similar to the medicine T1A (circular). To do.
  • the region of interest RA includes a marking area indicating the marking “133”.
  • the processing unit 10 region of interest setting unit 10D
  • a rectangular region of interest RB (smaller than the region of interest RA) is set.
  • the region of interest RB also includes a marking area indicating the marking “133”.
  • one third of the distance from the center to the end of the captured image iT1 with respect to the ⁇ X direction and the ⁇ Y direction is set as a threshold value (this value is an example), and the drug It is assumed that the position of T1B exceeds the threshold value in the X-axis direction and the Y-axis direction.
  • the processing unit 10 sets a rectangular region of interest RC (smaller than RB) while avoiding the side region EC and the “1” portion of the marking.
  • the region of interest RC includes a portion indicating “33” in the marking region indicating the marking “133”.
  • FIG. 10B is a diagram showing the positions of the centers CA, CB, and CC of the regions of interest RA, RB, and RC.
  • the center CA is the center of the medicine T1A, that is, the center of the captured image iT1, and the centers CB and CC are moved to the center side (+ X side) of the captured image iT1 (the movement amount of the center CC> the movement amount of the center CB). .
  • the marking is not shown.
  • the processing unit 10 sets the position, shape, and size of the template in correspondence with the region of interest set in this way (step S158 in FIG. 8: template generation step). Specifically, the smaller the region of interest is, the smaller the template is generated. The larger the amount of movement of the region of interest is, the larger the template is moved relative to the master image, and the template is moved in the same direction as the direction of movement of the region of interest relative to the light source. Note that the processing unit 10 (template generation unit 10E) generates a template including a marking region indicating marking (or a part thereof).
  • FIG. 11A and FIG. 11B are diagrams showing the setting of the region of interest when the medicine T1 is present at the center and the end in the + Y-axis direction (reference symbols are T1A and T1D, respectively).
  • the processing unit 10 region-of-interest setting unit 10D sets a region of interest RA that is circular (similar to the drug T1) for the drug T1A in the same manner as in FIGS. 10A and 10B.
  • the processing unit 10 (region of interest setting unit 10D) is strongly influenced by the + Y side region (the + Y side light source) with respect to the drug T1D (the drug T1 is present at the end in the + Y direction in the captured image iT2).
  • the region of interest RD is set so as not to include the region) and the side region ED (the region of interest RD is smaller than the region of interest RA).
  • FIG. 11B is a diagram showing the positions of the centers CA and CD of the regions of interest RA and RD.
  • the center CA is the center of the medicine T1A (that is, the center of the photographed image) as in FIG. 10B, and the center CD is moved to the center side ( ⁇ Y side; arrow direction) of the photographed image.
  • 12A and 12B are diagrams illustrating setting of a region of interest when a medicine is in a portrait orientation in the situation of FIGS. 10A and 10B.
  • the processing unit 10 determines that the drug T1E (drug T1 is present at the center of the captured image iT3) is circular (similar to the drug T1) as in FIGS. 10A and 10B.
  • the region of interest RE is set.
  • the processing unit 10 performs the ⁇ X side region (the ⁇ X side light source 13) of the medicine T1F.
  • the region of interest RF is set so as not to include the side region EF (region of interest RF is smaller than the region of interest RE).
  • the rectangular region of interest RG is set so as not to include the ⁇ X side and the side region EG of the drug T1G (region of interest RG Is smaller than the region of interest RF).
  • FIG. 12B is a diagram showing the positions of the centers CE, CF, and CG of the regions of interest RE, RF, and RG as in FIGS. 10B and 11B.
  • the center CE is the center of the medicine T1E, that is, the center of the photographed image iT3, and the centers CF and CG are moved to the center side (+ X side) of the photographed image iT3 (the amount of movement of the center CG> the amount of movement of the center CF). .
  • the marking is not shown.
  • the processing unit 10 template generation unit 10E sets the position, shape, and size of the template corresponding to the region of interest thus set (FIG. 8).
  • Step S158 template generation step).
  • the processing unit 10 (medicine detection unit 10C) in, for example, step S140 (medicine detection step).
  • the processing unit 10 collates the template with the region of interest. Then, it is determined whether the medicine to be audited and the medicine indicated by the master image are the same medicine (step S160: collation process). At the time of collation, the orientation may be adjusted by rotating at least one of the region of interest and the template. The size may be adjusted by enlarging or reducing at least one of the region of interest and the template.
  • the processing unit 10 outputs information indicating whether or not the medicine to be audited and the medicine indicated by the master image are the same (described later).
  • step S170 collation process. Determine whether or not. If the determination is affirmative (YES in step S170), the process proceeds to step S180. If the determination is negative (NO in step S170), the process returns to step S130 and an image of the next medicine to be audited is acquired and collated (step S140: collation). Step).
  • step S180 it is determined whether or not the collation has been completed for all the drugs described in the prescription (all the drugs to be packaged in the packaging bag TP), and the determination is positive for the other drugs described in the prescription.
  • Steps S120 to S170 are repeated until it is determined, and if the determination is affirmative (YES in step S180), the process proceeds to step S190.
  • the processing unit 10 (collation unit 10F) determines whether or not the processing for all the packaging bags TP included in the medicine bandage PB has been completed, and performs the processing of steps S110 to S180 until the determination is affirmed. (Drug detection process, region of interest setting process, template setting process, collation process) are repeated.
  • the processing unit 10 (the collation unit 10F and the display control unit 10G) displays the collation result (information indicating whether or not the medicine to be audited and the medicine indicated by the master image are the same). ) Is output (step S200: collation step). For example, as shown in FIG. 13, a list of images of audited medicines determined as “medicine T1 (see FIGS. 7 and 9)” is displayed on the monitor 32. In addition, the fact that “the drug to be audited and the drug indicated by the master image are the same, similar, or dissimilar” may be displayed for each audited drug and / or for each master image. May be displayed.
  • the processing unit 10 (collation unit 10F) may store the collation result (collation result 20E) in the storage unit 20 (step S200: collation process).
  • the first embodiment it is possible to avoid or reduce drug shape distortion, blurring, reflection of edges, and the like caused by the position of a drug to be audited.
  • the influence is small, and the robustness of collation accuracy can be increased.
  • Dispensing Audit Support Device 10 Processing Unit 10A Prescription Information Input Unit 10B Imaging Unit 10C Drug Detection Unit 10D Region of Interest Setting Unit 10E Template Generation Unit 10F Verification Unit 10G Display Control Unit 10H Communication Unit 12 Illumination Unit 13 Light Source 15A Camera 15B Camera 16 Prescription Reader 20 Storage unit 20A Prescription information 20B Master image 20C Attribute information 20D Drug image 20E Verification result 30 Display unit 32 Monitor 40 Operation unit 50 Transport mechanism CA Center CB Center CC Center CD Center CE Center CF Center CG Center EB Side area EC Side area ED side region EF side region EG side region F1 stamp F2 stamp F3 stamp L light PA imaging optical axis PB medicine bandage RA region of interest RB region of interest RC region of interest RD region of interest RF region of interest RG region of interest S100-S 00 Dispensing audit support method steps T1 agent T1A drug T1B drug T1C drug T1D drug T1E drug T1F drug T1G drug TP packing bag iM

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Chemical & Material Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Medicinal Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Pharmacology & Pharmacy (AREA)
  • Veterinary Medicine (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Medical Preparation Storing Or Oral Administration Devices (AREA)
  • Image Analysis (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
PCT/JP2018/016282 2017-05-30 2018-04-20 調剤監査支援装置及び調剤監査支援方法 WO2018221066A1 (ja)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2019522022A JP6757851B2 (ja) 2017-05-30 2018-04-20 調剤監査支援装置及び調剤監査支援方法
EP18809549.1A EP3633609A1 (en) 2017-05-30 2018-04-20 Dispensing inspection assistance device and dispensing inspection assistance method
CN201880029204.4A CN110603567B (zh) 2017-05-30 2018-04-20 配药监查辅助装置以及配药监查辅助方法
US16/662,233 US11594322B2 (en) 2017-05-30 2019-10-24 Dispensing audit support apparatus and dispensing audit support method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017106815 2017-05-30
JP2017-106815 2017-05-30

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/662,233 Continuation US11594322B2 (en) 2017-05-30 2019-10-24 Dispensing audit support apparatus and dispensing audit support method

Publications (1)

Publication Number Publication Date
WO2018221066A1 true WO2018221066A1 (ja) 2018-12-06

Family

ID=64454718

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/016282 WO2018221066A1 (ja) 2017-05-30 2018-04-20 調剤監査支援装置及び調剤監査支援方法

Country Status (5)

Country Link
US (1) US11594322B2 (zh)
EP (1) EP3633609A1 (zh)
JP (1) JP6757851B2 (zh)
CN (1) CN110603567B (zh)
WO (1) WO2018221066A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116312938B (zh) * 2023-05-16 2023-08-04 西安交通大学医学院第一附属医院 基于大数据分析的配药信息处理方法、系统及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0981748A (ja) 1995-09-11 1997-03-28 Sumitomo Electric Ind Ltd 輪郭形状の識別方法および自動選別装置
JP2006189354A (ja) * 2005-01-07 2006-07-20 Ckd Corp 外観検査装置及びｐｔｐ包装機
JP2010190786A (ja) * 2009-02-19 2010-09-02 Takeda Chem Ind Ltd 固形製剤の印字検査方法及び装置
JP2014067342A (ja) 2012-09-27 2014-04-17 Fujifilm Corp 薬剤検査支援装置及び方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7046842B2 (en) * 1999-08-17 2006-05-16 National Instruments Corporation System and method for color characterization using fuzzy pixel classification with application in color matching and color match location
US6944331B2 (en) * 2001-10-26 2005-09-13 National Instruments Corporation Locating regions in a target image using color matching, luminance pattern matching and hue plane pattern matching
JP2006280916A (ja) * 2005-03-11 2006-10-19 Yuyama Manufacturing Co Ltd 薬品秤量装置
US7883669B2 (en) * 2005-04-20 2011-02-08 Fluidigm Corporation Analysis engine and database for manipulating parameters for fluidic systems on a chip
CN100484474C (zh) * 2007-07-13 2009-05-06 华中科技大学 基于乳腺x线摄片的乳腺癌计算机辅助诊断系统
JP5196337B1 (ja) * 2011-04-28 2013-05-15 株式会社湯山製作所 薬剤鑑査装置、及び薬剤分包装置
KR102201005B1 (ko) * 2013-02-20 2021-01-08 가부시키가이샤 유야마 세이사쿠쇼 약제 감사 장치 및 약제 분포 시스템
US9958400B2 (en) * 2013-05-22 2018-05-01 Panasonic Healthcare Holdings Co., Ltd. Pill inspection apparatus and pill inspection method
JP6100136B2 (ja) * 2013-09-30 2017-03-22 富士フイルム株式会社 薬剤認識装置及び方法
US20170305589A1 (en) * 2014-09-25 2017-10-26 Yuyama Mfg. Co., Ltd. Inspection assistance system and tablet packaging device
WO2019039015A1 (ja) 2017-08-25 2019-02-28 富士フイルム株式会社 薬剤検査支援装置、画像処理装置、画像処理方法及びプログラム
CN112834518A (zh) * 2021-01-06 2021-05-25 优刻得科技股份有限公司 颗粒缺陷检测方法、系统、设备和介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0981748A (ja) 1995-09-11 1997-03-28 Sumitomo Electric Ind Ltd 輪郭形状の識別方法および自動選別装置
JP2006189354A (ja) * 2005-01-07 2006-07-20 Ckd Corp 外観検査装置及びｐｔｐ包装機
JP2010190786A (ja) * 2009-02-19 2010-09-02 Takeda Chem Ind Ltd 固形製剤の印字検査方法及び装置
JP2014067342A (ja) 2012-09-27 2014-04-17 Fujifilm Corp 薬剤検査支援装置及び方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3633609A4

Also Published As

Publication number Publication date
CN110603567B (zh) 2023-07-28
CN110603567A (zh) 2019-12-20
JPWO2018221066A1 (ja) 2020-03-19
EP3633609A4 (en) 2020-04-08
JP6757851B2 (ja) 2020-09-23
US11594322B2 (en) 2023-02-28
US20200058392A1 (en) 2020-02-20
EP3633609A1 (en) 2020-04-08

Similar Documents

Publication Publication Date Title
CN110418627B (zh) 药剂识别装置、药剂识别方法及药剂识别程序
JP5997120B2 (ja) 薬剤照合装置、薬剤照合システム、及び薬剤照合方法
TW201104508A (en) Stereoscopic form reader
US11404153B2 (en) Drug inspection assisting apparatus and drug inspection assisting method
US10937152B2 (en) Inspection support method and inspection support device
US20140355849A1 (en) System and method of using imprint analysis in pill identification
US20200098133A1 (en) Image Processing Method and Apparatus
US11341357B2 (en) Medicine inspection device, image processing device, image processing method, and program
JP7427684B2 (ja) 薬剤照合システム、薬剤管理方法及びプログラム
WO2019039015A1 (ja) 薬剤検査支援装置、画像処理装置、画像処理方法及びプログラム
JPWO2019039302A1 (ja) 薬剤検査支援装置、画像処理装置、画像処理方法及びプログラム
WO2020044933A1 (ja) 対象物照合装置及び対象物照合方法
WO2018221066A1 (ja) 調剤監査支援装置及び調剤監査支援方法
JP6047475B2 (ja) 画像認識装置、画像認識方法及び画像認識プログラム
JP5414879B1 (ja) 薬剤認識装置、薬剤認識方法及び薬剤認識プログラム
CN112614231A (zh) 信息显示方法与信息显示系统
JP6454249B2 (ja) 薬剤監査装置及び方法
JP7280361B2 (ja) 薬剤識別装置、薬剤識別方法及びプログラム
JP7375049B2 (ja) 画像処理装置及び方法
JP2020184144A (ja) 物品認識システム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18809549

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019522022

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2018809549

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2018809549

Country of ref document: EP

Effective date: 20200102